Strix Halo Wiki
A - Z
Changelog
Documentation
About An Otter Wiki
Toggle dark mode
Login
Menu
Home
Buyer's Guide
AI Guides
General Guides
Boards
PCs
GitHub Mirror
Discord Server
Page Index
AI
AI Capabilities Overview
llamacpp-performance
llamacpp-with-ROCm
vLLM
Guides
Sixunited AXB35
Power Mode and Fan Control
Replacing Thermal Interfaces On GMKtec EVO-X2
Restoring Corrupted BIOS
Buyer's Guide
C-States
External GPU
Hardware Monitoring
Power Modes and Performance
VM iGPU Passthrough
Hardware
Boards
Sixunited AXB35
Firmware
Framework Desktop Mainboard
MeeGoPad 100AM
Sixunited STHT1
PCs
Beelink GTR9 Pro
Bosgame M5
Corsair AI Workstation 300
FEVM FA-EX9
Framework Desktop
GEEKOM A9 Mega
GMKtec EVO-X2
HP Z2 Mini G1a
Minisforum MS-S1 MAX
NIMO AI MiniPC
Home
AI
Page Index
Toggle page headings
A
AI Capabilities Overview
Intro
GPU Compute
Comparison to other available options
Setup
Basic System Setup
Docker Images
Memory Limits
ROCm
Performance Tips
LLMs
llama.cpp
Additional Resources
Image/Video Generation
L
llamacpp-performance
llama-bench Basics
Performance Testing
Long Context Length Testing
Bonus ROCm numbers
Bonus Tuned ROCm numbers
llamacpp-with-ROCm
Building llama.cpp with ROCm
ROCm
rocWMMA
2025-10-31 rocWMMA
V
vLLM
Current Status
Build Steps
0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9